fix：youtube 360P 每次6条

pc_youtube.py

@@ -5,10 +5,14 @@ from utils.Logger import log
 from utils.createBrowserDriver import create
 from utils.filse import save_json
 from api.index import importJson, getReptileTask, importJsonPath
-from utils.index import convert_to_traditional, yt_dlp_download,convert_string_to_time
-# from pytube import YouTube
+from utils.index import convert_to_traditional, yt_dlp_download, convert_string_to_time
+from pytube import YouTube
+from datetime import datetime
 import os
 from config.settings import get_base_file_url
+from selenium.webdriver.common.action_chains import ActionChains
+
+
 def reptile(browser=None, search_word=""):
     """
 
@@ -22,25 +26,39 @@ def reptile(browser=None, search_word=""):
     # 打开网页
     url = f'https://www.youtube.com/results?search_query={search_word}'
     browser.get(url)
+    # time.sleep(2)
     classify_video_list = browser.find_elements('xpath',
                                                 "//div[@id='contents']//ytd-video-renderer//div[@id='title-wrapper']//a")
-    element_author_list = browser.find_elements('xpath',"//div[@id='contents']//ytd-video-renderer//ytd-channel-name//yt-formatted-string/a")
-    element_time_list = browser.find_elements('xpath',"//div[@id='contents']//ytd-video-renderer//ytd-video-meta-block//div[@id='metadata-line']/span[2]")
-    # print(classify_item_list)
+    element_author_list = browser.find_elements('xpath',
+                                                "//div[@id='contents']//ytd-video-renderer//ytd-channel-name//yt-formatted-string/a")
+    element_time_list = browser.find_elements('xpath',
+                                              "//div[@id='contents']//ytd-video-renderer//ytd-video-meta-block//div[@id='metadata-line']/span[2]")
+    # 时间长度集合
+    # elemnet_logtime_list = browser.find_elements('xpath',"//div[@id='contents']//ytd-video-renderer//ytd-thumbnail//ytd-thumbnail-overlay-time-status-renderer//span")
+    # 获取目录下所有文件名
+    # file_names = os.listdir(os.path.join(os.path.abspath("./"), "reptile_data", "youtube"))
     length = len(classify_video_list)
     for index in range(length):
-        if 0 <= index < length:
         title = classify_video_list[index].get_attribute('title')
         link = classify_video_list[index].get_attribute('href')
+        id = link.split("?")[1].split("&")[0].replace("v=", "")
+        url = f'https://www.youtube.com/watch?v={id}'
+        # is_repeat = False
+        # for item in file_names:
+        #     # print("id——1："+f'{id}.mp4')
+        #     # print("id——2：" + item)
+        #     if f'{id}.mp4' == item:
+        #         is_repeat = True
+        #     else:
+        #         is_repeat = False
+        # print(is_repeat)
+        if index < 6 and YouTube(url).length // 60 < 60:
             # yt = YouTube(link)
             # link = "https://www.youtube.com/watch?v=7q88m5MQRhE"
             # print(link)
             # author = element_author_list[index].text
             # file_url = './' + link + '.mp4'
-            id = link.split("?")[1].split("&")[0].replace("v=","")
-            url = f'https://www.youtube.com/watch?v={id}'
             base_urr = get_base_file_url()
-            log.debug(url)
             releaseTime = ""
             try:
                 releaseTime = str(convert_string_to_time(element_time_list[index].text))
@@ -48,6 +66,7 @@ def reptile(browser=None, search_word=""):
                 releaseTime = str(time.time())
             # 下载视频
             state_download = yt_dlp_download(url, 'youtube')
+            log.debug(url)
             file_http_src = f'{base_urr}youtube/{id}.mp4'
             if state_download:
                 # 组装数据
@@ -62,8 +81,10 @@ def reptile(browser=None, search_word=""):
                     "releaseTime": releaseTime
                 }
                 data.append(obj)
-            else:
-                return False
+            else :
+                print("")
+                # return False
+                # log.debug("")
 
     if len(data) > 0:
         # 保存json文件到本地

utils/index.py

@@ -84,7 +84,11 @@ def yt_dlp_download(url, name):
     geo = ""
     # --get-url
     video_selection = f''
-    download_options = f'-f mp4 -vU'
+    # 清晰度
+    definition = f'18' # 360p
+    # definition = f'18' # 720p
+    # definition = f'24' # 1080p
+    download_options = f'-f {definition} -vU'
     other_options = f'--verbose'
     # 要执行的 shell 命令
     command = f'yt-dlp {options} {network_options} {geo} {video_selection} {download_options} {other_options} -- {url}'